ek826 commited on
Commit
ed6a75b
1 Parent(s): 5d56fad

Upload GPTJForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +46 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "instruct-gpt-j-fp16",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gptj",
15
+ "n_embd": 4096,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 28,
19
+ "n_positions": 2048,
20
+ "quantization_config": {
21
+ "llm_int8_enable_fp32_cpu_offload": false,
22
+ "llm_int8_skip_modules": null,
23
+ "llm_int8_threshold": 6.0,
24
+ "load_in_8bit": true
25
+ },
26
+ "resid_pdrop": 0.0,
27
+ "rotary_dim": 64,
28
+ "summary_activation": null,
29
+ "summary_first_dropout": 0.1,
30
+ "summary_proj_to_labels": true,
31
+ "summary_type": "cls_index",
32
+ "summary_use_proj": true,
33
+ "task_specific_params": {
34
+ "text-generation": {
35
+ "do_sample": true,
36
+ "max_length": 50,
37
+ "temperature": 1.0
38
+ }
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "tokenizer_class": "GPT2Tokenizer",
42
+ "torch_dtype": "float16",
43
+ "transformers_version": "4.28.1",
44
+ "use_cache": true,
45
+ "vocab_size": 50400
46
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.28.1"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63642fa955a986baec2eb213ee0bd0b57dc6bd8c959c6e3dc4840280afea6ce4
3
+ size 6586359097